Hi everyone! I built Spotter because I kept having the same experience while traveling: I'd see something interesting like a dish I couldn't name, a building with no sign, wildlife I'd never seen, etc., and I just wanted to know what I was looking at (and some of the history behind it)! The options were: - Google Lens: Filled with shopping links, SEO spam, and links to annoying articles I don't really care much about. - Take a photo, upload to ChatGPT/Claude: This works, but feels really clunky and full of friction when you're standing on a street corner - Google Maps: works if it's a restaurant or building you're right next to, but doesn't work well if it's far away or it can't be "mapped" (like a person, sculpture, or something moving, etc.) So I built what I wanted: point camera, tap, get the crash course on it. A few things I'll note: - Multiple synopsis modes: quick summary when you're in a hurry, historical deep-dive when you want the full story. Some of my friends like different versions of each. Premium lets you build your own custom modes if you have a particular topic you're really into or if you have your own preferences. - Chat to keep exploring if you want to go deeper - Everything saves automatically as a travel journal with photo + GPS. You can even ask follow-up questions from it down the line! - Model-agnostic backend: Gemini might be the "best" for now, but people might prefer different providers down the line / have personal preferences towards a specific one. Premium lets you swap from Gemini to GPT or a local LLM (some people told me they like going to places where connection is limited, so I figured I'd try that out too) It's a solo project, still super rough around some edges, but it solves a problem I had for a while now. Would love your feedback! Happy to answer any questions!

Spotter - The AI Travel Companion

Point. Snap. Know the story behind anything you see.

Point. Snap. Know the story behind anything you see.